Hello! 👋
M.Sc. Mathematics @ IIT Delhi · Machine Learning · NLP · GenAI
I’m an M.Sc. Mathematics student at IIT Delhi, building ML systems across computer vision, NLP, and tabular data. I care about the work behind the metric: strong baselines, data-leak checks, reproducible pipelines, and evaluation that reflects the real task.
Deep metric-learning verifier for genuine versus forged signatures. I exposed two systemic data leaks in the ICDAR benchmark, then reached ROC-AUC 0.986 and cross-dataset AUC 0.877 with writer-independent evaluation.
NLP compliance auditor for 14 CCPA dark-pattern classes across a 6.7K-sample corpus. It compares a 22-feature baseline with fine-tuned DistilBERT under a skeleton-aware split.
Indian tech-salary predictor built as a reproducible ML delivery project. It cleans 110K records and deploys tuned CatBoost with MAE around ₹1.60 LPA, tracked with MLflow, DVC, and Docker.
US domestic-flight delay classifier restricted to information available before takeoff. It compares logistic regression, random forest, neural-network, and XGBoost baselines.
Indian Institute of Technology Delhi
University of Rajasthan
Stanford University / DeepLearning.AI · supervised and unsupervised learning, recommenders, and neural networks
DeepLearning.AI · CNNs, RNNs, sequence models, attention, and transformers
IBM · LLMs, retrieval-augmented generation, agentic AI, and vector databases